相关论文: MAGMaR Shared Task System Description: Video Retri…

We present Omni-Embed-Nemotron, a unified multimodal retrieval embedding model developed to handle the increasing complexity of real-world information needs. While Retrieval-Augmented Generation (RAG) has significantly advanced language…

Recent advancements in large language models (LLMs) have driven interest in billion-scale retrieval models with strong generalization across retrieval tasks and languages. Additionally, progress in large vision-language models has created…

Multimodal retrieval is the task of aggregating information from queries across heterogeneous modalities to retrieve desired targets. State-of-the-art multimodal retrieval models can understand complex queries, yet they are typically…

Efficiently retrieving and synthesizing information from large-scale multimodal collections has become a critical challenge. However, existing video retrieval datasets suffer from scope limitations, primarily focusing on matching…

Online video web content is richly multimodal: a single video blends vision, speech, ambient audio, and on-screen text. Retrieval systems typically treat these modalities as independent retrieval sources, which can lead to noisy and subpar…

State-of-the-art retrieval models typically address a straightforward search scenario, in which retrieval tasks are fixed (e.g., finding a passage to answer a specific question) and only a single modality is supported for both queries and…

Multi-modal retrieval has seen tremendous progress with the development of vision-language models. However, further improving these models require additional labelled data which is a huge manual effort. In this paper, we propose a framework…

Videos inherently contain multiple modalities, including visual events, text overlays, sounds, and speech, all of which are important for retrieval. However, state-of-the-art multimodal language models like VAST and LanguageBind are built…

Universal multimodal embedding models have achieved great success in capturing semantic relevance between queries and candidates. However, current methods either condense queries and candidates into a single vector, potentially limiting the…

The rapid advancement of Multimodal Large Language Models (MLLMs) has extended CLIP-based frameworks to produce powerful, universal embeddings for retrieval tasks. However, existing methods primarily focus on natural images, offering…

Unified multimodal embedding spaces have become the standard interface for cross-modal retrieval and multimodal RAG, and recent audio-video-text (AVT) encoders extend this setting to three modalities. Such encoders can produce a joint…

Multimodal embedding models have been crucial in enabling various downstream tasks such as semantic similarity, information retrieval, and clustering over different modalities. However, existing multimodal embeddings like VLM2Vec, E5-V, GME…

Multimodal document retrieval systems have shown strong progress in aligning visual and textual content for semantic search. However, most existing approaches remain heavily English-centric, limiting their effectiveness in multilingual…

In this paper, we present an overview of a multimodal system to indexing and searching video sequence by the content that has been developed within the REGIMVid project. A large part of our system has been developed as part of TRECVideo…

In this paper, we introduce OmniEval, a benchmark for evaluating omni-modality models like MiniCPM-O 2.6, which encompasses visual, auditory, and textual inputs. Compared with existing benchmarks, our OmniEval has several distinctive…

Video search has become the main routine for users to discover videos relevant to a text query on large short-video sharing platforms. During training a query-video bi-encoder model using online search logs, we identify a modality bias…

Multimodal embedding models aim to map heterogeneous inputs, such as text, images, videos, and audio, into a shared semantic space. However, existing methods and benchmarks remain largely limited to partial modality coverage, making it…

We present a new state-of-the-art on the text to video retrieval task on MSRVTT and LSMDC benchmarks where our model outperforms all previous solutions by a large margin. Moreover, state-of-the-art results are achieved with a single model…

With the explosive growth of web videos and emerging large-scale vision-language pre-training models, e.g., CLIP, retrieving videos of interest with text instructions has attracted increasing attention. A common practice is to transfer…

Visual-semantic embedding aims to learn a joint embedding space where related video and sentence instances are located close to each other. Most existing methods put instances in a single embedding space. However, they struggle to embed…